arXiv AI September 21, 2026 By Dan Zimmerman, Frank E. Bobe III, Amelia L. McCormack, Matthew Cook, Gregory D. Vetaw

LoRA Enhanced Contrastive Learning with SAS Vision Transformers

The paper presents a three‑stage, parameter‑efficient approach to improve automatic target recognition (ATR) with synthetic aperture sonar (SAS) data by adapting DINOv3 Vision Transformers. Stage 1 applies Low‑Rank Adaptation (LoRA) while freezing the backbone, which significantly boosts the area under the precision‑recall curve from 0.300 to 0.679. Subsequent hard‑negative mining and supervised contrastive learning stages show negligible impact, indicating that a single LoRA adaptation is sufficient for effective underwater ATR.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 22

Decoupled Pipeline with Proposal Reranking and Score Fusion for Positive-Unlabeled Marine Species Detection

arXiv:2607. 18700v1 Announce Type: cross Abstract: The FathomNetCLEF 2026 competition combines underwater object detection and fine-grained marine species classification under a positive-unlabeled evaluation setting.

By Robert James Brock, Sebastian Maximilian Krupa, Jason Kahei Tam

rag computer-vision fine-tuning benchmarks

arXiv Computer Vision

Aug 25

Spiking Neural Networks for Energy-Efficient Object Detection in Forward-Looking Sonar Imagery

arXiv:2608.22072v1 Announce Type: new Abstract: Autonomous underwater vehicles (AUVs) are increasingly important tools in industries ranging from research, to energy, to defense. AUVs are power-const...

By Gwenevere Frank, Gert Cauwenberghs

agents computer-vision benchmarks

arXiv Computer Vision

Sep 3

Improved Automatic Target Recognition in Synthetic Aperture Sonar Imagery Using Large Deep Neural Networks

The paper investigates Automatic Target Recognition (ATR) in Synthetic Aperture Sonar (SAS) imagery, comparing modern convolutional neural networks (CNNs) and transformer-based deep neural networks (DNNs). It examines how factors such as network size, architecture, pretraining methods, data augmentation, and regularization influence performance, aiming to identify the highest-performing model and provide a training roadmap for state‑of‑the‑art SAS‑ATR systems.

By C. J. Moore, Alex Hurt, Jordan Malof

llms computer-vision benchmarks

arXiv AI

Aug 21

Robust Cross-Modal Foundation Model Perception for Underwater Robots under Degraded Visual Conditions

arXiv:2608. 19710v1 Announce Type: cross Abstract: Reliable underwater robotic perception remains difficult because optical imagery degrades under turbidity, wavelength-dependent attenuation, low illumination, scattering, and blur.

By Mohammad Arif Ul Alam

robotics fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jul 28

A Comparison of Data Augmentation Methods for Training Deep Neural Networks on Synthetic Aperture Sonar

arXiv:2607. 23770v1 Announce Type: new Abstract: In this work we study Automatic Target Recognition (ATR) for Synthetic Aperture Sonar (SAS) data with a focus on deep neural networks (DNNs).

By C. J. Moore, Gregory D. Vetaw, Jordan Malof

llms

arXiv Computer Vision

Aug 26

Label-efficient underwater image classification with logistic regression on frozen foundation model embeddings

arXiv:2604.00313v3 Announce Type: replace Abstract: Underwater image classification is constrained by the cost of annotation and by the computational and methodological requirements of task-specific...

By Thomas Manuel Rost, Martina Figlia, F. Morgado-Dias, Marko Radeta

rag computer-vision benchmarks

One email a morning, machine-written

Related stories

Decoupled Pipeline with Proposal Reranking and Score Fusion for Positive-Unlabeled Marine Species Detection

Spiking Neural Networks for Energy-Efficient Object Detection in Forward-Looking Sonar Imagery

Improved Automatic Target Recognition in Synthetic Aperture Sonar Imagery Using Large Deep Neural Networks

Robust Cross-Modal Foundation Model Perception for Underwater Robots under Degraded Visual Conditions

A Comparison of Data Augmentation Methods for Training Deep Neural Networks on Synthetic Aperture Sonar

Label-efficient underwater image classification with logistic regression on frozen foundation model embeddings